CtrlK
BlogDocsLog inGet started
Tessl Logo

research-agent

Authoring playbook for building agents that search, read, and synthesize information into a report. Use this when the user wants an agent to research a topic, summarize sources, compare options, do competitive analysis, monitor news, generate briefs, or pull together a citation-backed report from the web or internal documents.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, actionable authoring playbook with copy-paste templates, a fixed output structure, and an explicit completion-criteria checklist that doubles as a validation gate. Its only weakness is redundancy between the system-prompt template, the 'Required behavioral rules' recap, and the second worked example.

Suggestions

Collapse the 'Required behavioral rules to enforce in the produced prompt' section into a one-line pointer to the template, since it restates freshness, output format, completion criteria, and citation discipline already embedded in the system prompt template.

Drop or shorten the trailing 'Worked example (full)' — its name, description, and completion-criteria excerpt duplicate the inline worked example and the template above it.

Tighten the 'Capabilities to prefer' list by merging the 'Do NOT attach code execution, spreadsheet, or email tools' line into the preceding numbered list as a closing note rather than a standalone paragraph.

DimensionReasoningScore

Conciseness

Mostly efficient templates and rules, but the 'Required behavioral rules to enforce' section and the second 'Worked example (full)' restate freshness, output format, completion criteria, and the description already present in the system-prompt template, so it could be tightened; it does not sink to level 1 because it avoids explaining concepts Claude already knows.

2 / 3

Actionability

Provides a copy-paste-ready system prompt template with placeholders, a fixed four-section output structure, a numbered completion checklist, and a concrete worked example — fully executable guidance rather than the incomplete/pseudocode middle anchor.

3 / 3

Workflow Clarity

Sequences the authoring process (identity → freshness → template → rules → capabilities → anti-patterns → example) and includes an explicit validation checkpoint via the six 'you are NOT done until' completion criteria with a 'Stop only when all applicable criteria are true' gate, matching the clear-sequence-with-checklist anchor.

3 / 3

Progressive Disclosure

Single-file skill with no bundle files and well-organized sections (When to use, Freshness policy, System prompt template, Required rules, Capabilities, Anti-patterns, Worked example); per the simple-skill guidance, well-organized sections with no need for external references score 3.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities and pairs them with an explicit 'Use this when' trigger clause listing natural user terms. It clearly answers both what the skill does and when to invoke it, with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'search, read, and synthesize information into a report' — plus research, summarize, compare, monitor news, and generate briefs, matching the 'lists multiple specific concrete actions' anchor rather than the partial 'names domain and some actions' level below.

3 / 3

Completeness

Explicitly answers both what ('Authoring playbook for building agents that search, read, and synthesize information into a report') and when ('Use this when the user wants an agent to research...'), with an explicit 'Use this when' trigger clause; not capped at 2 because the when-guidance is present and explicit.

3 / 3

Trigger Term Quality

Covers natural terms users would say — 'research a topic, summarize sources, compare options, do competitive analysis, monitor news, generate briefs' — giving broad coverage of common variations rather than only a few relevant keywords.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — citation-backed research/report agent authoring — with distinct triggers unlikely to fire for unrelated skills, rather than the 'somewhat specific but could overlap' middle anchor.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mastra-ai/mastra
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.